INDEX

Explanations

references to objects or concepts related to obstruction

oai_token-act-pair · gpt-3.5-turbo

occurrences of the abbreviation "ob"

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 guiActiveUnfocused

-0.99

EngineDebug

-0.93

agne

-0.82

 Prosper

-0.82

anwhile

-0.76

SEA

-0.73

terday

-0.68

gas

-0.67

-0.66

 Carlson

-0.66

POSITIVE LOGITS

lique

1.40

livion

1.32

structed

1.08

nox

1.05

eyed

1.02

olescent

0.98

tains

0.97

sole

0.93

olesc

0.92

obo

0.92

Activations Density 0.008%

references to objects or concepts related to obstruction

occurrences of the abbreviation "ob"

No Comments

No Known Activations